Multiple Object Tracking for Video-Based Sports Analysis.
Julius Gudauskas, Zygimantas Matusevicius · KTUePubl (Repository of Kaunas University of Technology) · 2021
Multiple object tracking (MOT) is a challenging task in computer vision. Many algorithms have been proposed to track multiple targets for video surveillance, team-sport analysis, or human–computer interaction. Recent studies have already indicated that multiple object tracking could provide valuable information in team sports analysis. Therefore, in this paper, we investigate object tracking techniques for paralympic team sport – goalball. Different tracking methods have been implemented and compared, evaluating prediction accuracy and performance speed in players and the ball tracking